An Optimized Bagging Ensemble Learning Approach Using BESTrees for Predicting Students’ Performance




machine learning, Weka, ensemble, student prediction, bagging, optimization techniques, hyperparameters, BESTrees, decision tree


Every academic institution's goal is to identify students who require additional assistance and take appropriate actions to improve their performance. As such, various research studies have focused on developing prediction models that can detect correlated patterns influencing students' performance, dropout, collaboration, and engagement. Among the influential predictive models available, the bagging ensemble has captured the interest of researchers seeking to improve prediction accuracy over single classifiers. However, prior work in this area has focused mainly on selecting single classifiers as the base classifier of the bagging ensemble, with little to no further optimization of the proposed framework. This study aims to fill this gap by providing a bagging ensemble framework to optimize its hyperparameters and achieve improved prediction accuracy. The proposed model used the Weka BESTrees data mining tool and Math language course student dataset from UCI Machine Learning Repository. Based on the experiments performed, the proposed bagging optimization technique can effectively increase the accuracy of a traditional bagging ensemble method. It reveals further that the proposed BESTrees framework can achieve an optimized performance when trained with the appropriate hyperparameters and hill climb metrics.


Author Biography

Edmund Evangelista, Zayed University

Dr. Edmund Evangelista is an Assistant Professor at the College of Technological Innovation at Zayed University (Abu Dhabi Campus). He received his Ph.D. in Information Technology from Saint Paul University Philippines. His primary field of research is Machine Learning and Software Engineering. Before joining Zayed University, he has over eighteen years of experience working both in the IT Industry and in IT Academia in countries like Oman, Kuwait, and the Philippines. He has held positions as Team Leader, Software Engineer, and Web/Moodle Developer within the IT industry. In academia, he taught at various universities in the Philippines such as the University of St. Louis, St. Mary’s University, and Cagayan State University for both undergraduate and graduate programs.




How to Cite

Evangelista, E. (2023). An Optimized Bagging Ensemble Learning Approach Using BESTrees for Predicting Students’ Performance. International Journal of Emerging Technologies in Learning (iJET), 18(10), pp. 150–165.